模糊聚类分析在分区负荷预测中的应用

分区负荷预测通常直接按行政区域划分预测区域,没有考虑同一行政区内可能存在电力负荷增长规律有较大差异的情况。通过模糊聚类的方法,按下一级行政区域中负荷变化规律的近似程度,实现新的分区,有利于改善分区负荷预测的预测效果。针对聚类过程中各项聚类指标对用电量水平影响力不同的问题,引入了加权标定方法。以苏南5市为例进行了聚类分析,其结果和实际情况相符。

Application of fuzzy clustering in subarea load forecasting

Traditionally, subarea load forecasting divides the area by the administrative region directly, without considering that the features of load increasing has great difference even in the same region. The method of fuzzy clustering is used to divide the area by the similar feature of load increasing. The new division is promising to improve the result of subarea load forecasting. According to different influence of evident degree of clustering index to power load, the weighted demarcating method is inducted. The result of clustering analysis of five cities in southern Jiangsu is in accordance with reality.